docs: refresh world-class submission evidence

This commit is contained in:
yaojingang
2026-06-14 12:10:31 +08:00
parent e03d5b2c74
commit 07274b4c50
19 changed files with 57 additions and 49 deletions
+4 -4
View File
@@ -63,7 +63,7 @@
<dt>Ledger</dt><dd><code>pending</code></dd>
<dt>Submission</dt><dd><code>evidence/world_class/submissions/provider-holdout.json</code></dd>
</dl>
<section><h4>Commands</h4><ul class="commands"><li><span>prepare submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions</code></li><li><span>validate intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>review queue</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh ledger</span><code>python3 scripts/yao.py world-class-ledger .</code></li><li><span>guard claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></section>
<section><h4>Commands</h4><ul class="commands"><li><span>prepare submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions</code></li><li><span>validate intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>review queue</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh ledger</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li><li><span>guard claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></section>
<div class="mini-grid">
<section><h4>Must Collect</h4><ul><li>provider-backed model run</li><li>observed timing</li><li>observed token metadata</li></ul></section>
<section><h4>Success Checks</h4><ul><li>reports/output_execution_runs.json summary.model_executed_count &gt; 0</li><li>reports/output_execution_runs.json summary.timing_observed_count &gt; 0</li><li>reports/output_execution_runs.json summary.token_observed_count &gt; 0</li><li>reports/skill_os2_audit.json item provider-holdout status becomes pass</li></ul></section>
@@ -77,7 +77,7 @@
<dt>Ledger</dt><dd><code>pending</code></dd>
<dt>Submission</dt><dd><code>evidence/world_class/submissions/human-adjudication.json</code></dd>
</dl>
<section><h4>Commands</h4><ul class="commands"><li><span>prepare submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions</code></li><li><span>validate intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>review queue</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh ledger</span><code>python3 scripts/yao.py world-class-ledger .</code></li><li><span>guard claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></section>
<section><h4>Commands</h4><ul class="commands"><li><span>prepare submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions</code></li><li><span>validate intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>review queue</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh ledger</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li><li><span>guard claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></section>
<div class="mini-grid">
<section><h4>Must Collect</h4><ul><li>real reviewer identity</li><li>blind A/B decisions</li><li>answer key unopened until decisions exist</li></ul></section>
<section><h4>Success Checks</h4><ul><li>reports/output_review_adjudication.json summary.pending_count == 0</li><li>reports/output_review_adjudication.json summary.judgment_count == summary.pair_count</li><li>reports/output_review_adjudication.json summary.invalid_decision_count == 0</li><li>reports/skill_os2_audit.json item human-adjudication status becomes pass</li></ul></section>
@@ -91,7 +91,7 @@
<dt>Ledger</dt><dd><code>pending</code></dd>
<dt>Submission</dt><dd><code>evidence/world_class/submissions/native-permission-enforcement.json</code></dd>
</dl>
<section><h4>Commands</h4><ul class="commands"><li><span>prepare submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions</code></li><li><span>validate intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>review queue</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh ledger</span><code>python3 scripts/yao.py world-class-ledger .</code></li><li><span>guard claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></section>
<section><h4>Commands</h4><ul class="commands"><li><span>prepare submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions</code></li><li><span>validate intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>review queue</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh ledger</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li><li><span>guard claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></section>
<div class="mini-grid">
<section><h4>Must Collect</h4><ul><li>real target client or external installer runtime guard</li><li>native enforcement flag or externally accepted guard proof</li><li>residual risk retained for fallback targets</li></ul></section>
<section><h4>Success Checks</h4><ul><li>reports/runtime_permission_probes.json summary.native_enforcement_count &gt; 0</li><li>reports/runtime_permission_probes.json summary.failure_count == 0</li><li>reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence</li><li>reports/skill_os2_audit.json item native-permission-enforcement status becomes pass</li></ul></section>
@@ -105,7 +105,7 @@
<dt>Ledger</dt><dd><code>pending</code></dd>
<dt>Submission</dt><dd><code>evidence/world_class/submissions/native-client-telemetry.json</code></dd>
</dl>
<section><h4>Commands</h4><ul class="commands"><li><span>prepare submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions</code></li><li><span>validate intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>review queue</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh ledger</span><code>python3 scripts/yao.py world-class-ledger .</code></li><li><span>guard claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></section>
<section><h4>Commands</h4><ul class="commands"><li><span>prepare submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions</code></li><li><span>validate intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>review queue</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh ledger</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li><li><span>guard claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></section>
<div class="mini-grid">
<section><h4>Must Collect</h4><ul><li>real external client source</li><li>metadata-only event</li><li>local-first import path</li></ul></section>
<section><h4>Success Checks</h4><ul><li>reports/adoption_drift_report.json summary.source_types.external &gt; 0</li><li>reports/adoption_drift_report.json summary.adoption_sample_count &gt; 0</li><li>reports/skill_os2_audit.json item native-client-telemetry status becomes pass</li></ul></section>